The new 1X World Model enables NEO to turn any request into an AI capability on demand.1X Technologies
1X has rolled out a major AI update for its humanoid robot NEO, introducing what it calls the 1X World Model.
The company says the system allows NEO to turn simple voice or text prompts into new physical skills, even in situations it has never encountered before.
At the core of the update is a video-based AI model grounded in real-world physics.
Instead of relying only on pre-programmed behaviors or large volumes of human-operated robot data, NEO can now learn from internet-scale video and apply that knowledge directly to the physical world, the company said in a release.
This approach is meant to close a long-standing gap in humanoid robotics: transferring digital intelligence into reliable physical action.
By learning from video that captures how humans interact with objects, NEO can generalize its behavior across unfamiliar environments and tasks.
According to 1X, this is the first major step toward robots that can continuously teach themselves, rather than waiting for engineers or operators to define each new capability.
From prompts to action
With the 1X World Model, users can give NEO a short instruction, either by voice or text.
The robot uses its cameras to understand the scene, generates visual predictions of future actions, and then converts those predictions into precise movements using an inverse dynamics model.
‘After years of developing our World Model and making NEO’s design as close to human as possible, NEO can now learn from internet-scale video and apply that knowledge directly to the physical world,” Bernt Børnich, CEO and Founder of 1X said.
“With the ability to transform any prompt into new actions—even without prior examples—this marks the starting point of NEO’s ability to teach itself to master nearly anything you could think to ask.”
In a recently released demonstration video, NEO is shown completing everyday tasks such as packing a lunch box. Even when objects differ from what it has seen before, the robot is able to plan and execute the task smoothly.
More notably, NEO also handles entirely new actions without prior training examples.
These include opening a sliding door, operating a toilet seat, ironing clothes, and brushing a human’s hair.
The company says this reflects the transfer of broad human knowledge captured in video into robotic behavior.
“With the 1X World Model, you can turn any prompt into a fully autonomous robot action — even with tasks and objects NEO’s never seen before,” said Daniel Ho, AI Researcher at 1X.
Robots that teach themselves
Beyond individual tasks, the update changes how NEO improves over time. Traditional humanoid robots depend heavily on data collected by human operators, which is slow and expensive.
The 1X World Model allows NEO to collect its own data as it interacts with the world, creating a self-reinforcing learning loop.
This also means NEO benefits as video models improve more broadly. Since the world model is built around video understanding, advances in video AI directly translate into better robotic capabilities.
Another focus is robustness. Homes are unpredictable, with changing lighting, clutter, and constant movement.
1X says the World Model helps NEO stay stable and adaptive in these conditions, generating reliable actions even when the environment shifts quickly.
NEO is currently available through 1X’s online store. Early access is priced at $20,000 with priority delivery planned for 2026, alongside a $499-per-month subscription option.
While still early, the update points to a future where humanoid robots learn less like machines and more like people.
